© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104459
    Prev
    Next
    INDEX
    Explanations

    references to numerical data and statistical or methodological elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.83
    <i>
    -0.78
    <blockquote>
    -0.69
    <sup>
    -0.67
    <em>
    -0.63
     
    -0.63
    <h2>
    -0.61
    <b>
    -0.59
    <h3>
    -0.57
    /
    -0.55
    POSITIVE LOGITS
     betweenstory
    0.82
     Wikiseite
    0.75
    
    0.70
     increí
    0.67
     queſta
    0.64
    lbrakk
    0.64
     Berlín
    0.63
    BibitemShut
    0.63
     Irán
    0.63
     callBack
    0.63
    Activations Density 0.173%

    No Known Activations